mlsanityData to 14 Oct 2026

Meta Architecture for Point Cloud Analysis

arXiv 2211.14462 ↗First posted 26 Nov 2022cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

Recent advances in 3D point cloud analysis bring a diverse set of network architectures to the field. However, the lack of a unified framework to interpret those networks makes any systematic comparison, contrast, or analysis challenging, and practically limits healthy development of the field. In this paper, we take the initiative to explore and propose a unified framework called PointMeta, to which the popular 3D point cloud analysis approaches could fit. This brings three benefits. First, it allows us to compare different approaches in a fair manner, and use quick experiments to verify any empirical observations or assumptions summarized from the comparison. Second, the big picture brought by PointMeta enables us to think across different components, and revisit common beliefs and key design decisions made by the popular approaches. Third, based on the learnings from the previous two analyses, by doing simple tweaks on the existing approaches, we are able to derive a basic building block, termed PointMetaBase. It shows very strong performance in efficiency and effectiveness through extensive experiments on challenging benchmarks, and thus verifies the necessity and benefits of high-level interpretation, contrast, and comparison like PointMeta. In particular, PointMetaBase surpasses the previous state-of-the-art method by 0.7%/1.4/%2.1% mIoU with only 2%/11%/13% of the computation cost on the S3DIS datasets.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). Builds on 36 of its 44 references that are in the map. First posted on arXiv 26 Nov 2022.

Builds on

36 of 44 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  8. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  9. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  10. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  12. 2020Point Transformercited by 1,470
24 more
  1. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  2. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  3. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  4. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  5. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  6. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  7. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  8. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  9. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  10. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 406
  11. 2021Conditional Positional Encodings for Vision Transformerscited by 406
  12. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  13. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  14. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
  15. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 207
  16. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  17. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 167
  18. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  19. 2020A Closer Look at Local Aggregation Operators in Point Cloud Analysiscited by 87
  20. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 72
  21. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  22. 2021ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learningcited by 29
  23. 2019Multinomial Distribution Learning for Effective Neural Architecture Searchcited by 17
  24. 2020Rethinking Performance Estimation in Neural Architecture Searchcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 12; 2025: 10; 2026: 12.

40 papers.

Sort:

By area:

  1. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  2. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 113
  3. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 110
  4. 2023OneFormer3D: One Transformer for Unified Point Cloud Segmentationcited by 95
  5. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 86
  6. 2024Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learningcited by 43
  7. 2024KPConvX: Modernizing Kernel Point Convolution with Kernel Attentioncited by 16
  8. 2024A Unified Framework for 3D Scene Understandingcited by 15
  9. 2024X-3D: Explicit 3D Structure Modeling for Point Cloud Recognitioncited by 11
  10. 2024Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classificationcited by 8
  11. 2024Dynamic 3D Point Cloud Sequences as 2D Videoscited by 7
  12. 2025Adaptive Margin Contrastive Learning for Ambiguity-aware 3D Semantic Segmentationcited by 4
28 more
  1. 2025Fourier Decomposition for Explicit Representation of 3D Point Cloud Attributescited by 4
  2. 2025All in One: Visual-Description-Guided Unified Point Cloud Segmentationcited by 4
  3. 2024SP2T: Sparse Proxy Attention for Dual-stream Point Transformercited by 3
  4. 2024Rethinking Attention Module Design for Point Cloud Analysiscited by 2
  5. 2025PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentationcited by 2
  6. 2026CDSeg: A Renderable Gaussian Carrier for Image-to-3D Label Transfercited by 2
  7. 2023Benchmarking Deep Learning Architectures for Urban Vegetation Point Cloud Semantic Segmentation from MLScited by 1
  8. 2024OpenTrench3D: A Photogrammetric 3D Point Cloud Dataset for Semantic Segmentation of Underground Utilitiescited by 1
  9. 2024Learning Localization of Body and Finger Animation Skeleton Joints on Three-Dimensional Models of Human Bodiescited by 1
  10. 2025SAMBLE: Shape-Specific Point Cloud Sampling for an Optimal Trade-Off Between Local Detail and Global Uniformitycited by 1
  11. 2025Enhancing point cloud analysis via neighbor aggregation correction based on cross-stage structure correlationcited by 1
  12. 2025Ambiguity-aware Point Cloud Segmentation by Adaptive Margin Contrastive Learningcited by 1
  13. 2026NPNet: A Non-Parametric Network with Adaptive Gaussian-Fourier Positional Encoding for 3D Classification and Segmentationcited by 1
  14. 2026RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodingscited by 1
  15. 2023Point Neighborhood Embeddingscited by 0
  16. 2024Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based Localizationcited by 0
  17. 2024Fine-grained Metrics for Point Cloud Semantic Segmentationcited by 0
  18. 2025PointVDP: Learning View-Dependent Projection by Fireworks Rays for 3D Point Cloud Segmentationcited by 0
  19. 2025Desensitizing for Improving Corruption Robustness in Point Cloud Classification through Adversarial Trainingcited by 0
  20. 2026REVNET: Rotation-Equivariant Point Cloud Completion via Vector Neuron Anchor Transformercited by 0
  21. 2026Efficient Point Cloud Processing with High-Dimensional Positional Encoding and Non-Local MLPscited by 0
  22. 2026Mamba Learns in Context: Structure-Aware Domain Generalization for Multi-Task Point Cloud Understandingcited by 0
  23. 2026Delaunay Canopy: Building Wireframe Reconstruction from Airborne LiDAR Point Clouds via Delaunay Graphcited by 0
  24. 2026Channel-Level Relation to Attentive Aggregation with Neighborhood-Homogeneity Constraint for Point Cloud Analysiscited by 0
  25. 2026RadiusFPS: Efficient Farthest Point Sampling on CPUs and GPUs via Spherical Voxel Pruningcited by 0
  26. 2026PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectificationcited by 0
  27. 2026ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generationcited by 0
  28. 2026Rationally Linearized MLPscited by 0